The role of pyroptosis-related genes in the diagnosis and subclassification of sepsis.
PloS one
Pyroptosis is a new form of programmed cell death recognized as crucial in developing sepsis. However, there is limited research on the mechanism of pyroptosis-related genes in sepsis-related from the Gene Expression Omnibus (GEO) database and standardized. The expression levels of pyroptosis-related genes were extracted, and differential expression analysis was conducted. A prediction model was constructed using random forest (RF), support vector machine (SVM), weighted gene co-expression new analysis (WGCNA), and nomogram techniques to assess the risk of sepsis. The relationship between pyroptosis-related subgroups and the immune microenvironment and inflammatory factors was studied using consistent clustering algorithms, principal component analysis (PCA), single-sample genomic enrichment analysis (ssGSEA), and immune infiltration. A risk prediction model based on 3 PRGs has been constructed and can effectively predict the risk of sepsis. Patients with sepsis can be divided into two completely different subtypes of pyroptosis-related clusters. Cluster B is highly correlated with the lower proportion of Th17 celld and has lower levels of expression of inflammatory factors. This study utilizes mechanical learning methods to further investigate the pathogenesis of sepsis, explore potential biomarkers, provide effective molecular targets for its diagnosis and treatment of sepsis.
10.1371/journal.pone.0293537
Multi-Branching Temporal Convolutional Network for Sepsis Prediction.
Wang Zekai,Yao Bing
IEEE journal of biomedical and health informatics
Sepsisis among the leading causes of morbidity and mortality in modern intensive care units. Accurate sepsis prediction is of critical importance to save lives and reduce medical costs. The rapid advancements in sensing and information technology facilitate the effective monitoring of patients' health conditions, generating a wealth of medical data, and provide an unprecedented opportunity for data-driven diagnosis of sepsis. However, real-world medical data are often complexly structured with a high level of uncertainty (e.g., missing values, imbalanced data). Realizing the full data potential depends on developing effective analytical models. In this paper, we propose a novel predictive framework with Multi-Branching Temporal Convolutional Network (MB-TCN) to model the complexly structured medical data for robust prediction of sepsis. The MB-TCN framework not only efficiently handles the missing value and imbalanced data issues but also effectively captures the temporal pattern and heterogeneous variable interactions. We evaluate the performance of the proposed MB-TCN in predicting sepsis using real-world medical data from PhysioNet/Computing in Cardiology Challenge 2019. Experimental results show that MB-TCN outperforms existing methods that are commonly used in current practice.
10.1109/JBHI.2021.3092835
Risk factor analysis and nomogram for predicting in-hospital mortality in ICU patients with sepsis and lung infection.
Ren Yinlong,Zhang Luming,Xu Fengshuo,Han Didi,Zheng Shuai,Zhang Feng,Li Longzhu,Wang Zichen,Lyu Jun,Yin Haiyan
BMC pulmonary medicine
BACKGROUND:Lung infection is a common cause of sepsis, and patients with sepsis and lung infection are more ill and have a higher mortality rate than sepsis patients without lung infection. We constructed a nomogram prediction model to accurately evaluate the prognosis of and provide treatment advice for patients with sepsis and lung infection. METHODS:Data were retrospectively extracted from the Medical Information Mart for Intensive Care (MIMIC-III) open-source clinical database. The definition of Sepsis 3.0 [10] was used, which includes patients with life-threatening organ dysfunction caused by an uncontrolled host response to infection, and SOFA score ≥ 2. The nomogram prediction model was constructed from the training set using logistic regression analysis, and was then internally validated and underwent sensitivity analysis. RESULTS:The risk factors of age, lactate, temperature, oxygenation index, BUN, lactate, Glasgow Coma Score (GCS), liver disease, cancer, organ transplantation, Troponin T(TnT), neutrophil-to-lymphocyte ratio (NLR), and CRRT, MV, and vasopressor use were included in the nomogram. We compared our nomogram with the Sequential Organ Failure Assessment (SOFA) score and Simplified Acute Physiology Score II (SAPSII), the nomogram had better discrimination ability, with areas under the receiver operating characteristic curve (AUROC) of 0.743 (95% C.I.: 0.713-0.773) and 0.746 (95% C.I.: 0.699-0.790) in the training and validation sets, respectively. The calibration plot indicated that the nomogram was adequate for predicting the in-hospital mortality risk in both sets. The decision-curve analysis (DCA) of the nomogram revealed that it provided net benefits for clinical use over using the SOFA score and SAPSII in both sets. CONCLUSION:Our new nomogram is a convenient tool for accurate predictions of in-hospital mortality among ICU patients with sepsis and lung infection. Treatment strategies that improve the factors considered relevant in the model could increase in-hospital survival for these ICU patients.
10.1186/s12890-021-01809-8
Interpretable machine-learning model for real-time, clustered risk factor analysis of sepsis and septic death in critical care.
Computer methods and programs in biomedicine
BACKGROUND AND OBJECTIVE:Interpretable and real-time prediction of sepsis and risk factor analysis could enable timely treatment by clinicians and improve patient outcomes. To develop an interpretable machine-learning model for the prediction and risk factor analysis of sepsis and septic death. METHODS:This is a retrospective observational cohort study based on the Medical Information Mart for Intensive Care (MIMIC-IV) dataset; 69,619 patients from the database were screened. The two outcomes include patients diagnosed with sepsis and the death of septic patients. Clinical variables from ICU admission to outcomes were analyzed: demographic data, vital signs, Glasgow Coma Scale scores, laboratory test results, and results for arterial blood gasses (ABGs). Model performance was compared using the area under the receiver operating characteristic curve (AUROC). Model interpretations were based on the Shapley additive explanations (SHAP), and the clustered analysis was based on the combination of K-means and dimensionality reduction algorithms of t-SNE and PCA. RESULTS:For the analysis of sepsis and septic death, 47,185 and 2480 patients were enrolled, respectively. The XGBoost model achieved a predictive value of area under the curve (AUC): 0.745 [0.731-0.759] for sepsis prediction and 0.8 [0.77, 0.828] for septic death prediction. The real-time prediction model was trained to predict by day and visualize the individual or combined risk factor effects on the outcomes based on SHAP values. Clustered analysis separated the two phenotypes with distinct risk factors among patients with septic death. CONCLUSION:The proposed real-time, clustered prediction model for sepsis and septic death exhibited superior performance in predicting the outcomes and visualizing the risk factors in a real-time and interpretable manner to distinguish and mitigate patient risks, thus promising immense potential in effective clinical decision making and comprehensive understanding of complex diseases such as sepsis.
10.1016/j.cmpb.2023.107772
A Machine Learning Model for Early Prediction and Detection of Sepsis in Intensive Care Unit Patients.
Journal of healthcare engineering
In today's scenario, sepsis is impacting millions of patients in the intensive care unit due to the fact that the mortality rate is increased exponentially and has become a major challenge in the field of healthcare. Such peoples require determinant care which increases the cost of the treatment by using a large number of resources because of the nonavailability of the resources. The treatment of sepsis is available in the early state, but treatment is not started at the right time, and then it converts to the advanced level of sepsis and increases the fatalities. Thus, an intensive analysis is required to detect and identify sepsis at the early stage. There are some models available that work based on the manual score and based on only the biomark features, but these are not fully automated. Some machine learning-based models are also available, which can reduce the mortality rate, but accuracy is not up to date. This paper proposes a machine learning model for early detecting and predicting sepsis in intensive care unit patients. Various models, random forest (RF), linear regression (LR), support vector machine (SVM), naive Bayes (NB), ensemble (of SVM, RF, NB, and LR), XGBoost, and proposed ensemble (of SVM, RF, NB, LR, and XGBoost), are simulated by using the collected data from intensive care unit patient's database that is based on the clinical laboratory values and vital signs. The performance of the models is evaluated by considering the same datasets. The balanced accuracy of RF, LR, SVM, NB, ensemble (of SVM, RF, NB, and LR), XGBoost, and proposed ensemble (of SVM, RF, NB, LR, and XGBoost) is 0.90, 0.73, 0.93, 0.74, 0.94, 0.95, and 0.96, respectively. It is also evident from the experimental results that the proposed ensemble model performs well as compared to the other models.
10.1155/2022/9263391
A time series driven model for early sepsis prediction based on transformer module.
BMC medical research methodology
Sepsis remains a critical concern in intensive care units due to its high mortality rate. Early identification and intervention are paramount to improving patient outcomes. In this study, we have proposed predictive models for early sepsis prediction based on time-series data, utilizing both CNN-Transformer and LSTM-Transformer architectures. By collecting time-series data from patients at 4, 8, and 12 h prior to sepsis diagnosis and subjecting it to various network models for analysis and comparison. In contrast to traditional recurrent neural networks, our model exhibited a substantial improvement of approximately 20%. On average, our model demonstrated an accuracy of 0.964 (± 0.018), a precision of 0.956 (± 0.012), a recall of 0.967 (± 0.012), and an F1 score of 0.959 (± 0.014). Furthermore, by adjusting the time window, it was observed that the Transformer-based model demonstrated exceptional predictive capabilities, particularly within the earlier time window (i.e., 12 h before onset), thus holding significant promise for early clinical diagnosis and intervention. Besides, we employed the SHAP algorithm to visualize the weight distribution of different features, enhancing the interpretability of our model and facilitating early clinical diagnosis and intervention.
10.1186/s12874-023-02138-6
Prediction of severe sepsis using SVM model.
Wang Shu-Li,Wu Fan,Wang Bo-Hang
Advances in experimental medicine and biology
Sepsis is an infectious condition that results in damage to organs. This paper proposes a severe sepsis model based on Support Vector Machine (SVM) for predicting whether a septic patient will become severe sepsis. We chose several clinical physiology of sepsis for identifying the features used for SVM. Based on the model, a medical decision support system is proposed for clinical diagnosis. The results show that the prognosis of a septic patient can be more precisely predicted than ever. We conduct several experiments, whose results demonstrate that the proposed model provides high accuracy and high sensitivity and can be used as a reminding system to provide in-time treatment in ICU.
10.1007/978-1-4419-5913-3_9
Construction and validation of a clinical prediction model for sepsis using peripheral perfusion index to predict in-hospital and 28-day mortality risk.
Scientific reports
Sepsis is a clinical syndrome caused by infection, leading to organ dysfunction due to a dysregulated host response. In recent years, its high mortality rate has made it a significant cause of death and disability worldwide. The pathophysiological process of sepsis is related to the body's dysregulated response to infection, with microcirculatory changes serving as early warning signals that guide clinical treatment. The Peripheral Perfusion Index (PI), as an indicator of peripheral microcirculation, can effectively evaluate patient prognosis. This study aims to develop two new prediction models using PI and other common clinical indicators to assess the mortality risk of sepsis patients during hospitalization and within 28 days post-ICU admission. This retrospective study analyzed data from sepsis patients treated in the Intensive Care Unit of Peking Union Medical College Hospital between December 2019 and June 2023, ultimately including 645 patients. LASSO regression and logistic regression analyses were used to select predictive factors from 35 clinical indicators, and two clinical prediction models were constructed to predict in-hospital mortality and 28-day mortality. The models' performance was then evaluated using ROC curve, calibration curve, and decision curve analyses. The two prediction models performed excellently in distinguishing patient mortality risk. The AUC for the in-hospital mortality prediction model was 0.82 in the training set and 0.73 in the validation set; for the 28-day mortality prediction model, the AUC was 0.79 in the training set and 0.73 in the validation set. The calibration curves closely aligned with the ideal line, indicating consistency between predicted and actual outcomes. Decision curve analysis also demonstrated high net benefits for the clinical utility of both models. The study shows that these two prediction models not only perform excellently statistically but also hold high practical value in clinical applications. The models can help physicians accurately assess the mortality risk of sepsis patients, providing a scientific basis for personalized treatment.
10.1038/s41598-024-78408-0
DeepAISE - An interpretable and recurrent neural survival model for early prediction of sepsis.
Artificial intelligence in medicine
Sepsis, a dysregulated immune system response to infection, is among the leading causes of morbidity, mortality, and cost overruns in the Intensive Care Unit (ICU). Early prediction of sepsis can improve situational awareness among clinicians and facilitate timely, protective interventions. While the application of predictive analytics in ICU patients has shown early promising results, much of the work has been encumbered by high false-alarm rates and lack of trust by the end-users due to the 'black box' nature of these models. Here, we present DeepAISE (Deep Artificial Intelligence Sepsis Expert), a recurrent neural survival model for the early prediction of sepsis. DeepAISE automatically learns predictive features related to higher-order interactions and temporal patterns among clinical risk factors that maximize the data likelihood of observed time to septic events. A comparative study of four baseline models on data from hospitalized patients at three different healthcare systems indicates that DeepAISE produces the most accurate predictions (AUCs between 0.87 and 0.90) at the lowest false alarm rates (FARs between 0.20 and 0.25) while simultaneously producing interpretable representations of the clinical time series and risk factors.
10.1016/j.artmed.2021.102036
Clinical Impact of a Sepsis Alert System Plus Electronic Sepsis Navigator Using the Epic Sepsis Prediction Model in the Emergency Department.
The Journal of emergency medicine
BACKGROUND:The Epic Sepsis Prediction Model (SPM) is a proprietary sepsis prediction algorithm that calculates a score correlating with the likelihood of an International Classification of Diseases, Ninth Revision code for sepsis. OBJECTIVE:This study aimed to assess the clinical impact of an electronic sepsis alert and navigator using the Epic SPM on time to initial antimicrobial delivery. METHODS:We performed a retrospective review of a nonrandomized intervention of an electronic sepsis alert system and navigator using the Epic SPM. Data from the SPM site (site A) was compared with contemporaneous data from hospitals within the same health care system (sites B-D) and historical data from site A. Nonintervention sites used a systemic inflammatory response syndrome (SIRS)-based alert without a sepsis navigator. RESULTS:A total of 5368 admissions met inclusion criteria. Time to initial antimicrobial delivery from emergency department arrival was 3.33 h (interquartile range [IQR] 2.10-5.37 h) at site A, 3.22 h (IQR 1.97-5.60; p = 0.437, reference site A) at sites B-D, and 6.20 h (IQR 3.49-11.61 h; p < 0.001, reference site A) at site A historical. After adjustment using matching weights, there was no difference in time from threshold SPM score to initial antimicrobial between contemporaneous sites. Adjusted time to initial antimicrobial improved by 2.87 h (p < 0.001) at site A compared with site A historical. CONCLUSIONS:Implementation of an electronic sepsis alert system plus navigator using the Epic SPM showed no difference in time to initial antimicrobial delivery between the contemporaneous SPM alert plus sepsis navigator site and the SIRS-based electronic alert sites within the same health care system.
10.1016/j.jemermed.2023.02.025
MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis.
Rosnati Margherita,Fortuin Vincent
PloS one
With a mortality rate of 5.4 million lives worldwide every year and a healthcare cost of more than 16 billion dollars in the USA alone, sepsis is one of the leading causes of hospital mortality and an increasing concern in the ageing western world. Recently, medical and technological advances have helped re-define the illness criteria of this disease, which is otherwise poorly understood by the medical society. Together with the rise of widely accessible Electronic Health Records, the advances in data mining and complex nonlinear algorithms are a promising avenue for the early detection of sepsis. This work contributes to the research effort in the field of automated sepsis detection with an open-access labelling of the medical MIMIC-III data set. Moreover, we propose MGP-AttTCN: a joint multitask Gaussian Process and attention-based deep learning model to early predict the occurrence of sepsis in an interpretable manner. We show that our model outperforms the current state-of-the-art and present evidence that different labelling heuristics lead to discrepancies in task difficulty. For instance, when predicting sepsis five hours prior to onset on our new realistic labels, our proposed model achieves an area under the ROC curve of 0.660 and an area under the PR curve of 0.483, whereas the (less interpretable) previous state-of-the-art model (MGP-TCN) achieves 0.635 AUROC and 0.460 AUPR and the popular commercial InSight model achieves 0.490 AUROC and 0.359 AUPR.
10.1371/journal.pone.0251248
A Comparison of the Quick-SOFA and Systemic Inflammatory Response Syndrome Criteria for the Diagnosis of Sepsis and Prediction of Mortality: A Systematic Review and Meta-Analysis.
Serafim Rodrigo,Gomes José Andrade,Salluh Jorge,Póvoa Pedro
Chest
BACKGROUND:Several studies were published to validate the quick Sepsis-related Organ Failure Assessment (qSOFA), namely in comparison with the systemic inflammatory response syndrome (SIRS) criteria. We performed a systematic review and meta-analysis with the aim of comparing the qSOFA and SIRS in patients outside the ICU. METHODS:We searched MEDLINE, CINAHL, and the Web of Science database from February 23, 2016 until June 30, 2017 to identify full-text English-language studies published after the Sepsis-3 publication comparing the qSOFA and SIRS and their sensitivity or specificity in diagnosing sepsis, as well as hospital and ICU length of stay and hospital mortality. Data extraction from the selected studies followed the recommendations of the Meta-analyses of Observational Studies in Epidemiology group and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses statement. RESULTS:From 4,022 citations, 10 studies met the inclusion criteria. Pooling all the studies, a total of 229,480 patients were evaluated. The meta-analysis of sensitivity for the diagnosis of sepsis comparing the qSOFA and SIRS was in favor of SIRS (risk ratio [RR], 1.32; 95% CI, 0.40-2.24; P < .0001; I = 100%). One study described the specificity for the diagnosis of infection comparing SIRS (84.4%; 95% CI, 76.2-90.6) with the qSOFA (97.3%; 95% CI < 92.1-99.4); the qSOFA demonstrated better specificity. The meta-analysis of the area under the receiver operating characteristic curve of six studies comparing the qSOFA and SIRS favored the qSOFA (RR, 0.03; 95% CI, 0.01-0.05; P = .002; I = 48%) as a predictor of inhospital mortality. CONCLUSIONS:The SIRS was significantly superior to the qSOFA for sepsis diagnosis, and the qSOFA was slightly better than the SIRS in predicting hospital mortality. The association of both criteria could provide a better model to initiate or escalate therapy in patients with sepsis. SYSTEMATIC REVIEW REGISTRATION:PROSPERO CRD42017067645.
10.1016/j.chest.2017.12.015
Development and Validation of the Prediction Model of Sepsis in Patients After Percutaneous Nephrolithotomy and Sepsis Progresses to Septic Shock.
Journal of endourology
To study the predictors of sepsis and the progression of sepsis to septic shock in patients after percutaneous nephrolithotomy (PCNL) and to establish and validate predictive models. The patients were assigned to either the development cohort or the validation cohort depending on their hospital. In the development cohort, univariate and multivariate logistic regression analyses were used to screen independent risk factors for sepsis after PCNL and sepsis progression to septic shock. Nomogram prediction models were established according to the related independent risk factors. Areas under the receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA) were used to estimate the discrimination, calibration, and clinical usefulness of the prediction models, respectively. The two sets of models were further validated on the validation cohort. In the development cohort, the risk factors for sepsis after PCNL were diabetes, urine nitrite, staghorn calculi, HU value, albumin-globulin ratio, and high-sensitivity C-reactive protein/albumin ratio. The pre- and postoperative white blood cell counts were risk factors for the progression of sepsis to septic shock. The area under the ROC curve value for predicting sepsis risk was 0.891 and that for predicting septic shock risk was 0.981 in the development cohort; in the validation cohort, these values were 0.893 and 0.996, respectively. In the development cohort, the calibration test values in the sepsis and septic shock cohorts were 0.946 and 0.634, respectively; in the validation cohort, these values were 0.739 and 0.208, respectively. DCA of the model in the sepsis and septic shock cohorts showed threshold probabilities of 10%-90% in the development cohort; in the validation cohort, these values were 10%-90%. The individualized nomogram prediction models can help improve the early identification of patients who are at higher risk of developing sepsis after PCNL and the progression of sepsis to septic shock to avoid further damage.
10.1089/end.2022.0384
Clinical characteristics and risk factors associated with ICU-acquired infections in sepsis: A retrospective cohort study.
Frontiers in cellular and infection microbiology
Intensive care unit (ICU)-acquired infection is a common cause of poor prognosis of sepsis in the ICU. However, sepsis-associated ICU-acquired infections have not been fully characterized. The study aims to assess the risk factors and develop a model that predicts the risk of ICU-acquired infections in patients with sepsis. Methods:We retrieved data from the Medical Information Mart for Intensive Care (MIMIC) IV database. Patients were randomly divided into training and validation cohorts at a 7:3 ratio. A multivariable logistic regression model was used to identify independent risk factors that could predict ICU-acquired infection. We also assessed its discrimination and calibration abilities and compared them with classical score systems. Results:Of 16,808 included septic patients, 2,871 (17.1%) developed ICU-acquired infection. These patients with ICU-acquired infection had a 17.7% ICU mortality and 31.8% in-hospital mortality and showed a continued rise in mortality from 28 to 100 days after ICU admission. The classical Systemic Inflammatory Response Syndrome Score (SIRS), Sequential Organ Failure Assessment (SOFA), Oxford Acute Severity of Illness Score (OASIS), Simplified Acute Physiology Score II (SAPS II), Logistic Organ Dysfunction Score (LODS), Charlson Comorbidity Index (CCI), and Acute Physiology Score III (APS III) scores were associated with ICU-acquired infection, and cerebrovascular insufficiency, Gram-negative bacteria, surgical ICU, tracheostomy, central venous catheter, urinary catheter, mechanical ventilation, red blood cell (RBC) transfusion, LODS score and anticoagulant therapy were independent predictors of developing ICU-acquired infection in septic patients. The nomogram on the basis of these independent predictors showed good calibration and discrimination in both the derivation (AUROC = 0.737; 95% CI, 0.725-0.749) and validation (AUROC = 0.751; 95% CI, 0.734-0.769) populations and was superior to that of SIRS, SOFA, OASIS, SAPS II, LODS, CCI, and APS III models. Conclusions:ICU-acquired infections increase the likelihood of septic mortality. The individualized prognostic model on the basis of the nomogram could accurately predict ICU-acquired infection and optimize management or tailored therapy.
10.3389/fcimb.2022.962470
A predictive model for the risk of sepsis within 30 days of admission in patients with traumatic brain injury in the intensive care unit: a retrospective analysis based on MIMIC-IV database.
European journal of medical research
PURPOSE:Traumatic brain injury (TBI) patients admitted to the intensive care unit (ICU) are at a high risk of infection and sepsis. However, there are few studies on predicting secondary sepsis in TBI patients in the ICU. This study aimed to build a prediction model for the risk of secondary sepsis in TBI patients in the ICU, and provide effective information for clinical diagnosis and treatment. METHODS:Using the MIMIC IV database version 2.0 (Medical Information Mart for Intensive Care IV), we searched data on TBI patients admitted to ICU and considered them as a study cohort. The extracted data included patient demographic information, laboratory indicators, complications, and other clinical data. The study cohort was divided into a training cohort and a validation cohort. In the training cohort, variables were screened by LASSO (Least absolute shrinkage and selection operator) regression and stepwise Logistic regression to assess the predictive ability of each feature on the incidence of patients. The screened variables were included in the final Logistic regression model. Finally, the decision curve, calibration curve, and receiver operating character (ROC) were used to test the performance of the model. RESULTS:Finally, a total of 1167 patients were included in the study, and these patients were randomly divided into the training (N = 817) and validation (N = 350) cohorts at a ratio of 7:3. In the training cohort, seven features were identified as key predictors of secondary sepsis in TBI patients in the ICU, including acute kidney injury (AKI), anemia, invasive ventilation, GCS (Glasgow Coma Scale) score, lactic acid, and blood calcium level, which were included in the final model. The areas under the ROC curve in the training cohort and the validation cohort were 0.756 and 0.711, respectively. The calibration curve and ROC curve show that the model has favorable predictive accuracy, while the decision curve shows that the model has favorable clinical benefits with good and robust predictive efficiency. CONCLUSION:We have developed a nomogram model for predicting secondary sepsis in TBI patients admitted to the ICU, which can provide useful predictive information for clinical decision-making.
10.1186/s40001-023-01255-8
An interpretable machine learning model for real-time sepsis prediction based on basic physiological indicators.
European review for medical and pharmacological sciences
OBJECTIVE:In view of the important role of risk prediction models in the clinical diagnosis and treatment of sepsis, and the limitations of existing models in terms of timeliness and interpretability, we intend to develop a real-time prediction model of sepsis with high timeliness and clinical interpretability. PATIENTS AND METHODS:We used eight real-time basic physiological monitoring indicators of patients, including heart rate, respiratory rate, oxygen saturation, mean arterial pressure, systolic blood pressure, diastolic blood pressure, temperature and blood glucose, extracted three-hour dynamic feature sequences, and calculated 3 linear parameters (mean, standard deviation, and endpoint value), a 24-dimensional feature vector was constructed, and finally a real-time sepsis prediction model was constructed based on the Local Interpretable Model-Agnostic Explanation (LIME) interpretability method. RESULTS:The area under the receiver operating characteristic curve (AUROC), Accuracy and F1 scores of Extremely Randomized Trees we built were higher than those of other models, with AUROC above 0.76, showing the best performance. The Imbalance XGBoost has a high specificity (0.86) in predicting sepsis. The LIME local interpretable model we built can display a large amount of valid model prediction details for clinical workers' reference, including the prediction probability and the influence of each feature on the prediction result, thus effectively assisting the work of clinical workers and improving diagnostic efficiency. CONCLUSIONS:This model can provide real-time dynamic early warning of sepsis for critically ill patients under supervision and provide a reference for clinical decision support. At the same time, interpretive analysis of sepsis prediction models can improve the credibility of the models.
10.26355/eurrev_202305_32439
A robust scoring system to evaluate sepsis severity in an animal model.
Shrum Bradly,Anantha Ram V,Xu Stacey X,Donnelly Marisa,Haeryfar S M Mansour,McCormick John K,Mele Tina
BMC research notes
BACKGROUND:The lack of a reliable scoring system that predicts the development of septic shock and death precludes comparison of disease and/or treatment outcomes in animal models of sepsis. We developed a murine sepsis score (MSS) that evaluates seven clinical variables, and sought to assess its validity and reliability in an experimental mouse model of polymicrobial sepsis. METHODS:Stool collected from the cecum of C57BL/6 (B6) mice was dissolved in 0.9% normal saline (NS) and filtered, resulting in a fecal solution (FS) which was injected intraperitoneally into B6 mice. Disease severity was monitored by MSS during the experimental timeline. Blood and tissue samples were harvested for the evaluation of inflammatory changes after sepsis induction. The correlation between pro-inflammatory markers and MSS was assessed by the Spearman rank correlation coefficient. RESULTS:Mice injected with FS at a concentration of 90 mg/mL developed polymicrobial sepsis with a 75% mortality rate at 24 hours. The MSS was highly predictive of sepsis progression and mortality, with excellent discriminatory power, high internal consistency (Cronbach alpha coefficient = 0.92), and excellent inter-rater reliability (intra-class coefficient = 0.96). An MSS of 3 had a specificity of 100% for predicting onset of septic shock and death within 24 hours. Hepatic dysfunction and systemic pro-inflammatory responses were confirmed by biochemical and cytokine analyses where the latter correlated well with the MSS. Significant bacterial dissemination was noted in multiple organs. Furthermore, the liver, spleen, and intestine demonstrated histopathological evidence of injury. CONCLUSIONS:The MSS reliably predicts disease progression and mortality in an animal model of polymicrobial sepsis. More importantly, it may be used to assess and compare outcomes among various experimental models of sepsis, and serve as an ethically acceptable alternative to death as an endpoint.
10.1186/1756-0500-7-233
Dynamic Sepsis Prediction for Intensive Care Unit Patients Using XGBoost-Based Model With Novel Time-Dependent Features.
IEEE journal of biomedical and health informatics
Sepsis is a systemic inflammatory response caused by pathogens such as bacteria. Because its pathogenesis is not clear, the clinical manifestations of patients vary greatly, and the alarming incidence and mortality pose a great threat to patients and medical systems, especially in the ICU (Intensive Care Unit). The traditional judgment criteria have the problem of low specificity. Artificial intelligence models could greatly improve the accuracy of sepsis prediction and judgment. Based on the XGBoost machine learning framework taking demographic, vital signs, laboratory tests and medical intervention data as input, this paper proposes a novel model for dynamically predicting sepsis and assessing risk. To realize the model, two methods for feature construction are introduced. For the observed time-series data of vital signs and laboratory tests, the time-dependent method performs to construct the time-dependent characteristics after the statistical screening. For the clinical intervention data, the statistical counting method is applied to construct count-dependent characteristics. Moreover, a new objective function is proposed for the XGBoost framework, and the first-order and second-order gradients of the objective function are also given for model training. Compared with the state-of-the-art methods at present, the proposed model has the best performance, with AUROC improved by 5.4% on the MIMIC-III dataset and 2.1% on PhysioNet Challenge 2019 dataset. The data processing and training methods of this model can be conveniently applied in different electronic health record systems and has a wide application prospect.
10.1109/JBHI.2022.3171673
A scoping review of machine learning for sepsis prediction- feature engineering strategies and model performance: a step towards explainability.
Critical care (London, England)
BACKGROUND:Sepsis, an acute and potentially fatal systemic response to infection, significantly impacts global health by affecting millions annually. Prompt identification of sepsis is vital, as treatment delays lead to increased fatalities through progressive organ dysfunction. While recent studies have delved into leveraging Machine Learning (ML) for predicting sepsis, focusing on aspects such as prognosis, diagnosis, and clinical application, there remains a notable deficiency in the discourse regarding feature engineering. Specifically, the role of feature selection and extraction in enhancing model accuracy has been underexplored. OBJECTIVES:This scoping review aims to fulfill two primary objectives: To identify pivotal features for predicting sepsis across a variety of ML models, providing valuable insights for future model development, and To assess model efficacy through performance metrics including AUROC, sensitivity, and specificity. RESULTS:The analysis included 29 studies across diverse clinical settings such as Intensive Care Units (ICU), Emergency Departments, and others, encompassing 1,147,202 patients. The review highlighted the diversity in prediction strategies and timeframes. It was found that feature extraction techniques notably outperformed others in terms of sensitivity and AUROC values, thus indicating their critical role in improving sepsis prediction models. CONCLUSION:Key dynamic indicators, including vital signs and critical laboratory values, are instrumental in the early detection of sepsis. Applying feature selection methods significantly boosts model precision, with models like Random Forest and XG Boost showing promising results. Furthermore, Deep Learning models (DL) reveal unique insights, spotlighting the pivotal role of feature engineering in sepsis prediction, which could greatly benefit clinical practice.
10.1186/s13054-024-04948-6
Sepsis prediction, early detection, and identification using clinical text for machine learning: a systematic review.
Journal of the American Medical Informatics Association : JAMIA
OBJECTIVE:To determine the effects of using unstructured clinical text in machine learning (ML) for prediction, early detection, and identification of sepsis. MATERIALS AND METHODS:PubMed, Scopus, ACM DL, dblp, and IEEE Xplore databases were searched. Articles utilizing clinical text for ML or natural language processing (NLP) to detect, identify, recognize, diagnose, or predict the onset, development, progress, or prognosis of systemic inflammatory response syndrome, sepsis, severe sepsis, or septic shock were included. Sepsis definition, dataset, types of data, ML models, NLP techniques, and evaluation metrics were extracted. RESULTS:The clinical text used in models include narrative notes written by nurses, physicians, and specialists in varying situations. This is often combined with common structured data such as demographics, vital signs, laboratory data, and medications. Area under the receiver operating characteristic curve (AUC) comparison of ML methods showed that utilizing both text and structured data predicts sepsis earlier and more accurately than structured data alone. No meta-analysis was performed because of incomparable measurements among the 9 included studies. DISCUSSION:Studies focused on sepsis identification or early detection before onset; no studies used patient histories beyond the current episode of care to predict sepsis. Sepsis definition affects reporting methods, outcomes, and results. Many methods rely on continuous vital sign measurements in intensive care, making them not easily transferable to general ward units. CONCLUSIONS:Approaches were heterogeneous, but studies showed that utilizing both unstructured text and structured data in ML can improve identification and early detection of sepsis.
10.1093/jamia/ocab236
SSP: Early prediction of sepsis using fully connected LSTM-CNN model.
Rafiei Alireza,Rezaee Alireza,Hajati Farshid,Gheisari Soheila,Golzan Mojtaba
Computers in biology and medicine
BACKGROUND:Sepsis is a life-threatening condition that occurs due to the body's reaction to infections, and it is a leading cause of morbidity and mortality in hospitals. Early prediction of sepsis onset facilitates early interventions that promote the survival of suspected patients. However, reliable and intelligent systems for predicting sepsis are scarce. METHODS:This paper presents a novel technique called Smart Sepsis Predictor (SSP) to predict sepsis onset in patients admitted to an intensive care unit (ICU). SSP is a deep neural network architecture that encompasses long short-term memory (LSTM), convolutional, and fully connected layers to achieve early prediction of sepsis. SSP can work in two modes; Mode 1 uses demographic data and vital signs, and Mode 2 uses laboratory test results in addition to demographic data and vital signs. To evaluate SSP, we have used the 2019 PhysioNet/CinC Challenge dataset, which includes the records of 40,366 patients admitted to the ICU. RESULTS:To compare SSP with existing state-of-the-art methods, we have measured the accuracy of the SSP in 4-, 8-, and 12-h prediction windows using publicly available data. Our results show that the SSP performance in Mode 1 and Mode 2 is much higher than existing methods, achieving an area under the receiver operating characteristic curve (AUROC) of 0.89 and 0.92, 0.88 and 0.87, and 0.86 and 0.84 for 4 h, 8 h, and 12 h before sepsis onset, respectively. CONCLUSIONS:Using ICU data, sepsis onset can be predicted up to 12 h in advance. Our findings offer an early solution for mitigating the risk of sepsis onset.
10.1016/j.compbiomed.2020.104110
A PREDICTION MODEL FOR SEPSIS IN INFECTED PATIENTS: EARLY ASSESSMENT OF SEPSIS ENGAGEMENT.
Shock (Augusta, Ga.)
ABSTRACT:Purpose: To evaluate significant risk variables for sepsis incidence and develop a predictive model for rapid screening and diagnosis of sepsis in patients from the emergency department (ED). Methods: Sepsis-related risk variables were screened based on the PIRO (Predisposition, Insult, Response, Organ dysfunction) system. Training (n = 1,272) and external validation (n = 568) datasets were collected from Peking Union Medical College Hospital (PUMCH) and Beijing Tsinghua Changgung Hospital (BTCH), respectively. Variables were collected at the time of admission. Sepsis incidences were determined within 72 h after ED admissions. A predictive model, Early Assessment of Sepsis Engagement (EASE), was developed, and an EASE-based nomogram was generated for clinical applications. The predictive ability of EASE was evaluated and compared with the National Early Warning Score (NEWS) scoring system. In addition, internal and external validations were performed. Results: A total of 48 characteristics were identified. The EASE model, which consists of alcohol consumption, lung infection, temperature, respiration rate, heart rate, serum urea nitrogen, and white blood cell count, had an excellent predictive performance. The EASE-based nomogram showed a significantly higher area under curve (AUC) value of 86.5% (95% CI, 84.2%-88.8%) compared with the AUC value of 78.2% for the NEWS scoring system. The AUC of EASE in the external validation dataset was 72.2% (95% CI, 66.6%-77.7%). Both calibration curves of EASE in training and external validation datasets were close to the ideal model and were well-calibrated. Conclusions: The EASE model can predict and screen ED-admitted patients with sepsis. It demonstrated superior diagnostic performance and clinical application promise by external validation and in-parallel comparison with the NEWS scoring system.
10.1097/SHK.0000000000002170
Prediction of sepsis patients using machine learning approach: A meta-analysis.
Islam Md Mohaimenul,Nasrin Tahmina,Walther Bruno Andreas,Wu Chieh-Chen,Yang Hsuan-Chia,Li Yu-Chuan
Computer methods and programs in biomedicine
STUDY OBJECTIVE:Sepsis is a common and major health crisis in hospitals globally. An innovative and feasible tool for predicting sepsis remains elusive. However, early and accurate prediction of sepsis could help physicians with proper treatments and minimize the diagnostic uncertainty. Machine learning models could help to identify potential clinical variables and provide higher performance than existing traditional low-performance models. We therefore performed a meta-analysis of observational studies to quantify the performance of a machine learning model to predict sepsis. METHODS:A comprehensive literature search was conducted through the electronic database (e.g. PubMed, Scopus, Google Scholar, EMBASE, etc.) between January 1, 2000, and March 1, 2018. All the studies published in English and reporting the sepsis prediction using machine learning algorithms were considered in this study. Two authors independently extracted valuable information from the included studies. Inclusion and exclusion of studies were based on the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) guidelines. RESULTS:A total of 7 out of 135 studies met all of our inclusion criteria. For machine learning models, the pooled area under receiving operating curve (SAUROC) for predicting sepsis onset 3 to 4 h before, was 0.89 (95%CI: 0.86-0.92); sensitivity 0.81 (95%CI:0.80-0.81), and specificity 0.72 (95%CI:0.72-0.72) whereas the pooled SAUROC for SIRS, MEWS, and SOFA was 0.70, 0.50, and 0.78. Additionally, diagnostic odd ratio for machine learning, SIRS, MEWS, and SOFA was 15.17 (95%CI: 9.51-24.20), 3.23 (95%CI: 1.52-6.87), 31.99 (95% CI: 1.54-666.74), and 3.75(95%CI: 2.06-6.83). CONCLUSION:Our study findings suggest that the machine learning approach had a better performance than the existing sepsis scoring systems in predicting sepsis.
10.1016/j.cmpb.2018.12.027
Machine learning for the prediction of sepsis: a systematic review and meta-analysis of diagnostic test accuracy.
Intensive care medicine
PURPOSE:Early clinical recognition of sepsis can be challenging. With the advancement of machine learning, promising real-time models to predict sepsis have emerged. We assessed their performance by carrying out a systematic review and meta-analysis. METHODS:A systematic search was performed in PubMed, Embase.com and Scopus. Studies targeting sepsis, severe sepsis or septic shock in any hospital setting were eligible for inclusion. The index test was any supervised machine learning model for real-time prediction of these conditions. Quality of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) methodology, with a tailored Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) checklist to evaluate risk of bias. Models with a reported area under the curve of the receiver operating characteristic (AUROC) metric were meta-analyzed to identify strongest contributors to model performance. RESULTS:After screening, a total of 28 papers were eligible for synthesis, from which 130 models were extracted. The majority of papers were developed in the intensive care unit (ICU, n = 15; 54%), followed by hospital wards (n = 7; 25%), the emergency department (ED, n = 4; 14%) and all of these settings (n = 2; 7%). For the prediction of sepsis, diagnostic test accuracy assessed by the AUROC ranged from 0.68-0.99 in the ICU, to 0.96-0.98 in-hospital and 0.87 to 0.97 in the ED. Varying sepsis definitions limit pooling of the performance across studies. Only three papers clinically implemented models with mixed results. In the multivariate analysis, temperature, lab values, and model type contributed most to model performance. CONCLUSION:This systematic review and meta-analysis show that on retrospective data, individual machine learning models can accurately predict sepsis onset ahead of time. Although they present alternatives to traditional scoring systems, between-study heterogeneity limits the assessment of pooled results. Systematic reporting and clinical implementation studies are needed to bridge the gap between bytes and bedside.
10.1007/s00134-019-05872-y
A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients.
Wang Dong,Li Jinbo,Sun Yali,Ding Xianfei,Zhang Xiaojuan,Liu Shaohua,Han Bing,Wang Haixu,Duan Xiaoguang,Sun Tongwen
Frontiers in public health
Although numerous studies are conducted every year on how to reduce the fatality rate associated with sepsis, it is still a major challenge faced by patients, clinicians, and medical systems worldwide. Early identification and prediction of patients at risk of sepsis and adverse outcomes associated with sepsis are critical. We aimed to develop an artificial intelligence algorithm that can predict sepsis early. This was a secondary analysis of an observational cohort study from the Intensive Care Unit of the First Affiliated Hospital of Zhengzhou University. A total of 4,449 infected patients were randomly assigned to the development and validation data set at a ratio of 4:1. After extracting electronic medical record data, a set of 55 features (variables) was calculated and passed to the random forest algorithm to predict the onset of sepsis. The pre-procedure clinical variables were used to build a prediction model from the training data set using the random forest machine learning method; a 5-fold cross-validation was used to evaluate the prediction accuracy of the model. Finally, we tested the model using the validation data set. The area obtained by the model under the receiver operating characteristic (ROC) curve (AUC) was 0.91, the sensitivity was 87%, and the specificity was 89%. This newly established machine learning-based model has shown good predictive ability in Chinese sepsis patients. External validation studies are necessary to confirm the universality of our method in the population and treatment practice.
10.3389/fpubh.2021.754348
External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients.
JAMA internal medicine
Importance:The Epic Sepsis Model (ESM), a proprietary sepsis prediction model, is implemented at hundreds of US hospitals. The ESM's ability to identify patients with sepsis has not been adequately evaluated despite widespread use. Objective:To externally validate the ESM in the prediction of sepsis and evaluate its potential clinical value compared with usual care. Design, Setting, and Participants:This retrospective cohort study was conducted among 27 697 patients aged 18 years or older admitted to Michigan Medicine, the academic health system of the University of Michigan, Ann Arbor, with 38 455 hospitalizations between December 6, 2018, and October 20, 2019. Exposure:The ESM score, calculated every 15 minutes. Main Outcomes and Measures:Sepsis, as defined by a composite of (1) the Centers for Disease Control and Prevention surveillance criteria and (2) International Statistical Classification of Diseases and Related Health Problems, Tenth Revision diagnostic codes accompanied by 2 systemic inflammatory response syndrome criteria and 1 organ dysfunction criterion within 6 hours of one another. Model discrimination was assessed using the area under the receiver operating characteristic curve at the hospitalization level and with prediction horizons of 4, 8, 12, and 24 hours. Model calibration was evaluated with calibration plots. The potential clinical benefit associated with the ESM was assessed by evaluating the added benefit of the ESM score compared with contemporary clinical practice (based on timely administration of antibiotics). Alert fatigue was evaluated by comparing the clinical value of different alerting strategies. Results:We identified 27 697 patients who had 38 455 hospitalizations (21 904 women [57%]; median age, 56 years [interquartile range, 35-69 years]) meeting inclusion criteria, of whom sepsis occurred in 2552 (7%). The ESM had a hospitalization-level area under the receiver operating characteristic curve of 0.63 (95% CI, 0.62-0.64). The ESM identified 183 of 2552 patients with sepsis (7%) who did not receive timely administration of antibiotics, highlighting the low sensitivity of the ESM in comparison with contemporary clinical practice. The ESM also did not identify 1709 patients with sepsis (67%) despite generating alerts for an ESM score of 6 or higher for 6971 of all 38 455 hospitalized patients (18%), thus creating a large burden of alert fatigue. Conclusions and Relevance:This external validation cohort study suggests that the ESM has poor discrimination and calibration in predicting the onset of sepsis. The widespread adoption of the ESM despite its poor performance raises fundamental concerns about sepsis management on a national level.
10.1001/jamainternmed.2021.2626